Invited Speakers
December 14, 2024 - West Meeting Room 111-112
Pre-registration form: https://forms.gle/YBCwn7L8N5AxExMG7
Speakers
Speakers
Assistant Professor, Ethics and Computational Technologies, Carnegie Mellon University
Assistant Professor, Ethics and Computational Technologies, Carnegie Mellon University
Reflections on Fairness Measurement: From Predictive to Generative AI
Reflections on Fairness Measurement: From Predictive to Generative AI
Abstract: In this talk, I will provide an overview of the algorithmic fairness literature, which has historically focused on predictive AI models, designed to automate or assist high-stakes decisions. I will contrast that line of work with the recently growing set of benchmarks, metrics, and measures for bias and unfairness through Generative AI. I will conclude with some reflections on conceptualizing and measuring GenAI unfairness, drawing on my past work.
Abstract: In this talk, I will provide an overview of the algorithmic fairness literature, which has historically focused on predictive AI models, designed to automate or assist high-stakes decisions. I will contrast that line of work with the recently growing set of benchmarks, metrics, and measures for bias and unfairness through Generative AI. I will conclude with some reflections on conceptualizing and measuring GenAI unfairness, drawing on my past work.
IBM Fellow
IBM Fellow
Harm Detectors and Guardian Models for LLMs: Implementations, Uses, and Limitations
Harm Detectors and Guardian Models for LLMs: Implementations, Uses, and Limitations
Abstract: Large language models (LLMs) are susceptible to a variety of harms, from non-faithful output to biased and toxic generations. Due to several limiting factors surrounding LLMs (training cost, API access, data availability, etc.), it may not always be feasible to impose direct safety constraints on a deployed model. Therefore, an efficient and reliable alternative is required. To this end, we present our ongoing efforts to create and deploy harm detectors and guardian models: compact classification models that provide labels for various harms. In addition to the models themselves, we discuss a wide range of uses for these detectors and guardian models - from acting as guardrails to enabling effective AI governance. We also deep dive into inherent sociotechnical challenges in their development.
Abstract: Large language models (LLMs) are susceptible to a variety of harms, from non-faithful output to biased and toxic generations. Due to several limiting factors surrounding LLMs (training cost, API access, data availability, etc.), it may not always be feasible to impose direct safety constraints on a deployed model. Therefore, an efficient and reliable alternative is required. To this end, we present our ongoing efforts to create and deploy harm detectors and guardian models: compact classification models that provide labels for various harms. In addition to the models themselves, we discuss a wide range of uses for these detectors and guardian models - from acting as guardrails to enabling effective AI governance. We also deep dive into inherent sociotechnical challenges in their development.
Postdoc, Stanford University
Postdoc, Stanford University
Fairness through Difference Awareness: Measuring Desired Group Discrimination in LLMs
Fairness through Difference Awareness: Measuring Desired Group Discrimination in LLMs
Abstract: Algorithmic fairness has conventionally adopted a perspective of racial color-blindness (i.e., difference unaware treatment). We contend that in a range of important settings, group difference awareness matters. First, we present a taxonomy of such settings, such as in the legal system where it can be legally permissible to discriminate (e.g., Native Americans sometimes have privileged legal status, men enter the compulsory draft in America while women do not). Second, we present a benchmark suite that spans eight different settings for a total of 16k questions that enables us to assess for difference awareness. Third, we show that difference awareness is a distinct dimension of fairness and that existing bias mitigation strategies may backfire on this dimension.
Abstract: Algorithmic fairness has conventionally adopted a perspective of racial color-blindness (i.e., difference unaware treatment). We contend that in a range of important settings, group difference awareness matters. First, we present a taxonomy of such settings, such as in the legal system where it can be legally permissible to discriminate (e.g., Native Americans sometimes have privileged legal status, men enter the compulsory draft in America while women do not). Second, we present a benchmark suite that spans eight different settings for a total of 16k questions that enables us to assess for difference awareness. Third, we show that difference awareness is a distinct dimension of fairness and that existing bias mitigation strategies may backfire on this dimension.
Professor of Philosophy, Australian National University
Professor of Philosophy, Australian National University
Evaluating the Ethical Competence of LLMs
Evaluating the Ethical Competence of LLMs
Abstract: Existing approaches to evaluating LLM ethical competence place too much emphasis on the verdicts—of permissibility and impermissibility—that they render. But ethical competence doesn’t consist in one’s judgments conforming to those of a cohort of crowdworkers. It consists in being able to identify morally relevant features, prioritise among them, associate them with reasons and weave them into a justified conclusion. We identify the limitations of existing evals for ethical competence, provide an account of moral reasoning that can ground better alternatives, and discuss the practical—and philosophical—implications if LLMs ultimately do prove to be adept moral reasoners.
Abstract: Existing approaches to evaluating LLM ethical competence place too much emphasis on the verdicts—of permissibility and impermissibility—that they render. But ethical competence doesn’t consist in one’s judgments conforming to those of a cohort of crowdworkers. It consists in being able to identify morally relevant features, prioritise among them, associate them with reasons and weave them into a justified conclusion. We identify the limitations of existing evals for ethical competence, provide an account of moral reasoning that can ground better alternatives, and discuss the practical—and philosophical—implications if LLMs ultimately do prove to be adept moral reasoners.